add_sketch_relation

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare the mutation profile (readOnly=false, idempotent=false, destructive=false), so the description only needs to add context; it contributes the 'open sketch' prerequisite and the point-per-entity correspondence. It says nothing about failure behaviour (e.g. an over-constrained or already-defined sketch), whether duplicates are rejected, or what side effects the relation has on the sketch's degrees of freedom.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The core action is front-loaded in one sentence, followed by two compact parameter notes keyed to their argument names. Dense but efficient; no filler, though the vertex sentence packs several ideas into one parenthetical that could be split for readability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained. However, this is a mutation tool with three parameters and zero schema description coverage, and the description omits the mapping of entity count to point count per relation and any error/constraint behaviour, leaving real gaps for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description carries the burden; it does explain points (one sketch-coordinate point per involved entity) and vertex (one boolean flag per point, selecting an endpoint/centre instead of the curve) plus the 'point first' ordering for coincident and midpoint. The relation parameter itself is never discussed, and the point count required per relation type is left unstated.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The first sentence gives a specific verb (adds) and resource (a geometric relation) plus a scope qualifier ('sketch entities of the open sketch'), which cleanly separates it from assembly-level add_mate and from add_sketch_dimension. It does not explicitly name a sibling as the wrong choice, but the sketch-scoped phrasing makes the boundary inferable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: the tool operates on 'the open sketch', so an agent can infer start_sketch must precede it, and the vertex note hints that coincident/midpoint may need point picking. There is no explicit guidance on when to use this versus add_sketch_dimension or when a relation is invalid for a given entity type.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.